© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 21466
    Prev
    Next
    INDEX
    Explanations

    structured sentences describing additional information or features

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating additional information or clarification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vised
    -0.75
    arbon
    -0.71
    arest
    -0.68
    ologically
    -0.65
    omorph
    -0.64
    aucus
    -0.63
    \\\\\\\\
    -0.63
    tip
    -0.62
    matter
    -0.62
    ipers
    -0.61
    POSITIVE LOGITS
     others
    1.07
    Another
    1.05
     also
    1.03
     another
    1.03
     other
    1.02
     Other
    1.02
    also
    0.99
     OTHER
    0.97
    Other
    0.97
     ALSO
    0.97
    Activations Density 0.282%

    No Known Activations